StepFun: Step 3.5 Flash

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

stepfun/step-3.5-flash

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

Specifications & capabilities

Input
text
Output
text
Context window · tokens
262144
Published model ID
step-3.5-flash
Capabilities
promptCaching, reasoning, streaming, structuredOutputs, toolCalling

Evaluations

41–60 / 95

LMArena

1,388.96

source id
lmarena
leaderboard name
LMArena Text Polish
dimension
general
metric
Arena rating
rank
139
sample size
1364
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1372.8259981678934
confidence upper
1405.0947077276032
Original result ↗

LMArena

1,351.272

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
139
sample size
641
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1326.6381641732655
confidence upper
1375.9058408217747
Original result ↗

LMArena

1,393.102

source id
lmarena
leaderboard name
LMArena Text Style Control German
dimension
style
metric
Arena rating
rank
140
sample size
1069
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1374.2030516731945
confidence upper
1412.000065694564
Original result ↗

LMArena

1,419.895

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Mathematical
dimension
style
metric
Arena rating
rank
141
sample size
3116
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1408.9627491199983
confidence upper
1430.8274121475201
Original result ↗

LMArena

1,376.406

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Entertainment And Sports And Media
dimension
factuality
metric
Arena rating
rank
141
sample size
9916
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1370.4744363585999
confidence upper
1382.3367219687536
Original result ↗

LMArena

1,350.171

source id
lmarena
leaderboard name
LMArena Text Korean
dimension
general
metric
Arena rating
rank
142
sample size
1073
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1331.3681898303787
confidence upper
1368.9733321720018
Original result ↗

LMArena

1,406.541

source id
lmarena
leaderboard name
LMArena Text Factuality Exclude Ties
dimension
factuality
metric
Arena rating
rank
144
sample size
43273
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1402.6201635189695
confidence upper
1410.4609180053762
Original result ↗

LMArena

1,403.837

source id
lmarena
leaderboard name
LMArena Text Style Control Spanish
dimension
style
metric
Arena rating
rank
145
sample size
2005
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1389.8455091206247
confidence upper
1417.8291824957446
Original result ↗

LMArena

1,420.228

source id
lmarena
leaderboard name
LMArena Text Hard Prompts English
dimension
general
metric
Arena rating
rank
146
sample size
16111
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1414.6407159707992
confidence upper
1425.8142868560833
Original result ↗

LMArena

1,415.952

source id
lmarena
leaderboard name
LMArena Text Factuality Overall
dimension
factuality
metric
Arena rating
rank
146
sample size
59430
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1412.93730974349
confidence upper
1418.9667041193588
Original result ↗

LMArena

1,437.43

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts
dimension
factuality
metric
Arena rating
rank
147
sample size
36890
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1433.6707280717378
confidence upper
1441.1895636106135
Original result ↗

LMArena

1,416.881

source id
lmarena
leaderboard name
LMArena Text English
dimension
general
metric
Arena rating
rank
147
sample size
25049
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1412.1472203714775
confidence upper
1421.614050853291
Original result ↗

LMArena

1,402.049

source id
lmarena
leaderboard name
LMArena Text Longer Query
dimension
general
metric
Arena rating
rank
149
sample size
22531
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1396.920139087082
confidence upper
1407.1771080534454
Original result ↗

LMArena

1,408.829

source id
lmarena
leaderboard name
LMArena Text Industry Medicine And Healthcare
dimension
general
metric
Arena rating
rank
150
sample size
4184
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1399.2642075594097
confidence upper
1418.3934549749224
Original result ↗

LMArena

1,407.783

source id
lmarena
leaderboard name
LMArena Text Industry Legal And Government
dimension
general
metric
Arena rating
rank
150
sample size
4612
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1398.6952773547437
confidence upper
1416.8707176395096
Original result ↗

LMArena

1,404.434

source id
lmarena
leaderboard name
LMArena Text Multi Turn
dimension
general
metric
Arena rating
rank
150
sample size
10329
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1397.9656452171994
confidence upper
1410.9016379553664
Original result ↗

LMArena

1,397.462

source id
lmarena
leaderboard name
LMArena Text Factuality Non English
dimension
factuality
metric
Arena rating
rank
151
sample size
34431
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1393.7028559301507
confidence upper
1401.2220516552495
Original result ↗

LMArena

1,428.332

source id
lmarena
leaderboard name
LMArena Text Style Control Expert
dimension
style
metric
Arena rating
rank
153
sample size
5247
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1419.8232816304912
confidence upper
1436.8401161202003
Original result ↗

LMArena

1,410.586

source id
lmarena
leaderboard name
LMArena Text Hard Prompts
dimension
general
metric
Arena rating
rank
153
sample size
37189
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1406.3246414836415
confidence upper
1414.847327337032
Original result ↗

LMArena

1,406.925

source id
lmarena
leaderboard name
LMArena Text Math
dimension
general
metric
Arena rating
rank
153
sample size
3403
evaluated at
2026-11-09T00:00:00.000Z
source model id
Step-3.5-Flash
confidence lower
1396.713777277292
confidence upper
1417.135952503252
Original result ↗

Published prices

1–7 / 7

stepfun-ai/Step-3.5-Flash ↗

$0.10

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)

stepfun-ai/Step-3.5-Flash ↗

$0.30

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)

step-3.5-flash ↗

$0.02

Inference provider
stepFun
Platform
StepFun
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input / 1M tokens

step-3.5-flash ↗

$0.10

Inference provider
stepFun
Platform
StepFun
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input / 1M tokens (cache miss)

step-3.5-flash ↗

$0.30

Inference provider
stepFun
Platform
StepFun
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output / 1M tokens

Provider specifications & access

1–2 / 2

Step 3.5 Flash ↗

source model id
step-3.5-flash
hosting
stepfun-global-hosted
platforms
  • StepFun
context length
256000
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • streaming
  • structuredOutputs
  • toolCalling

Step-3.5-Flash ↗

source model id
stepfun-ai/Step-3.5-Flash
hosting
siliconflow-hosted
platforms
  • SiliconFlow
max output tokens
65536
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • toolCalling

Source specification observations

1–3 / 3

siliconFlow ↗

field
context_length
value
262K
scope
source-model
source id
siliconFlow
confidence
1

stepFun ↗

field
context_length
value
256000
normalized value
256000
scope
source-model
source id
stepFun
confidence
1

siliconFlow ↗

field
max_output_tokens
value
66K
scope
source-model
source id
siliconFlow
confidence
1

Original sources

1–14 / 14

SiliconFlow · Model page ↗

StepFun · Model reference ↗

Hugging Face · Model repository ↗

DeepInfra · Model page ↗

SiliconFlow · Playground ↗

SiliconFlow · API documentation ↗

StepFun · Model documentation ↗

DeepInfra · Catalog ↗

Epoch AI · Catalog ↗

Hugging Face · Catalog ↗

Hugging Face · Catalog ↗

LMArena · Catalog ↗

SiliconFlow · Catalog ↗

StepFun · Catalog ↗

Source links

1–9 / 9

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace